Fisher Information

Follow this topic Ask about this topic

Momentum

4 papers in the last four weeks, level with the four weeks before. 0.0% of all new papers.

Jul 6Week of Sep 21

Latest papers 22

All topics

Fisher Simplicity in Kolmogorov-Arnold Networks and Multilayer Perceptrons
Sep 26, 2026Ami Tavory, Meir FederKolmogorov-Arnold Networks Multilayer Perceptrons
Meta Platforms Tel-Aviv, Israel · School of Electrical and Computer Engineering Tel-Aviv University Tel-Aviv, Israel
FedFIbOS: Fisher Importance based Optimal Submodelling for Heterogeneous Federated Learning
Sep 17, 2026Yasmeen Afzal, Jeremiah D. Deng, Haibo ZhangHeterogeneous Federated Learning Federated Learning
School of Computing, University of Otago, New Zealand · School of Computer Science and Engineering, University of New South Wales, Australia
Compression Hurts, Pooling Helps: Information Loss in Rayleigh-Scale Estimation from B-Mode Ultrasound
Sep 17, 2026D. Hudson Smith, Ahmer RazaUltrasound Density Ratio Estimation
Clemson University
The evolution of sex for artificial intelligence: a population-genetic framework for multigenerational model populations
Sep 16, 2026Giorgio F. GilestroArtificial Intelligence Models Population Dynamics
Department of Life Sciences, Imperial College London, London, UK
FAMPWQ: Fisher Information-based Adaptive Mixed Precision Weight Quantization for Effective LLM Inference
Aug 24, 2026Gongwei Lee, Ji Liu, Juncheng Jia +1Mixed-Precision Quantization LLM Inference Optimization
School of Computer Science and Technology, Soochow University, Suzhou, China · Hithink Research, Hangzhou, China · Electronic Engineering, Tsinghua University, Beijing, China
Fisher8: Stabilizing Neural Heteroscedastic Regression via Output-Layer Fisher Geometry
Aug 11, 2026Sumedh Vemuganti, Nickvash KaniFisher Information Heteroskedasticity
Electrical and Computer Engineering Department, University of Illinois at Urbana-Champaign
Fisher-R1: Training LLM Agents for Reliable Hypothesis Testing
Aug 7, 2026Jiacheng Miao, Jin Mu, Guanhua Chen +1Two-Sample Testing Large Language Model Agents
Department of Biomedical Data Science, Stanford University · Department of Genetics, Stanford University · Department of Biostatistics and Medical Informatics, University of Wisconsin–Madison +3
Information-Geometric Forward Policy Training in GFlowNets
Aug 4, 2026Yordan Raykov, Rodrigo VeigaGenerative Flow Networks Fisher Information Matrix
School of Mathematical Sciences, University of Nottingham, Nottingham, UK
Understanding and Overcoming Cross-modal Fusion Bias in Multimodal Anomaly Detection From A Fisher Information Perspective
Aug 2, 2026Kaifang Long, Lianbo Ma, Liming Liu +1Cross-Modal Fusion Multimodal Anomaly Detection
Northeastern University Shenyang, China · CATL Ningde, China
Fisher Widths: Local Learning Geometry and Anisotropic Recovery
Jul 22, 2026Vu Khac KyFisher Information Matrix Fisher Information
Department of Mathematics, FPT University, Vietnam
A Continual Validation, Updating, and Decision-Making Framework for Self-Adaptive Digital Twins via Robust Model Predictive Control: A Case Study in Additive Manufacturing
Jul 20, 2026Yi-Ping Chen, Ying-Kuan Tsai, Vispi Karkaria +3Cognitive Digital Twins Digital Twins
Department of Mechanical Engineering, Northwestern University · Department of Industrial Engineering and Management Science, Northwestern University
From Uncertainty to Stability and Fidelity: Guiding Sparse-View 3D Gaussian Splatting with Fisher Information
Jun 18, 2026Junbao Zhou, Qingshan Xu, Yuan Zhou +7Novel View Synthesis 3D Gaussian
Nanyang Technological University, Singapore · University of Science and Technology of China, China · Zhejiang University, China +1
Fisher Width: A Geometric Measure of Complexity on Statistical Manifolds
Jun 16, 2026Vu Khac KyFisher Information Data Manifold
Department of Mathematics, FPT University, Vietnam
Fisher-Guided Progressive Parameter Selection for Adaptive Fine-Tuning
Jun 8, 2026Ghodsiyeh Rostami, Po-Han Chen, Mahdi S. HosseiniParameter-Efficient Fine-Tuning Methods Parameter-Efficient Adaptation
Concordia University · Concordia University Mila - Québec AI Institute
Less is MoE: Trimming Experts in Domain-Specialist Language Models
Jun 4, 2026Haoze He, Xinkai Zou, Xuan Jiang +4Mixture-Of-Experts Experts
Carnegie Mellon University · UCSD · MIT
Measuring Model Robustness via Fisher Information: Spectral Bounds, Theoretical Guarantees, and Practical Algorithms
Jun 3, 2026Chong Zhang, Xiang Li, Jia Wang +2Robustness Verification Fisher Information Matrix
Xi’an Jiaotong-Liverpool University · The Chinese University of Hong Kong
Noise Schedule Design for Diffusion Models: An Optimal Control Perspective
May 21, 2026Seo Taek Kong, Weina Wang, R. SrikantDiffusion Models Optimal Control
ECE & CSL University of Illinois Urbana-Champaign · Computer Science Department Carnegie Mellon University · ECE, CSL & NCSA University of Illinois Urbana-Champaign
Complexity of Non-Log-Concave Sampling in Fisher Information
May 15, 2026Sinho Chewi, Andre WibisonoLog-Concave Distributions Optimal Sample Complexity
Yale University, Department of Statistics and Data Science. · Yale University, Department of Computer Science.
GEM-FI: Gated Evidential Mixtures with Fisher Modulation
May 5, 2026Marco Mustafa Mohammed, Fatemeh Daneshfar, Pietro LiòEvidential Uncertainty Dynamic Epistemic Logic
Department of Computer Engineering, Faculty of Engineering, University of Kurdistan, Sanandaj, Iran
Fisher Decorator: Refining Flow Policy via a Local Transport Map
Apr 20, 2026Xiaoyuan Cheng, Haoyu Wang, Wenxuan Yuan +4Flow Policies Fisher Information
University College London · Shanghai Jiao Tong University · Imperial College London +3
Geometric Metrics for MoE Specialization: From Fisher Information to Early Failure Detection
Apr 16, 2026Dongxin Guo, Jikun Wu, Siu Ming YiuMixture-Of-Experts Fisher Information
The University of Hong Kong · Hong Kong, China · Brain Investing Limited
FISHER: A Foundation Model for Multi-Modal Industrial Signal Comprehensive Representation
Jul 22, 2025Pingyi Fan, Anbai Jiang, Shuwei Zhang +9Fisher Information Encoders
Department of Electronic Engineering, Tsinghua University, Beijing, 100084, P. R. China · Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, 200240, P. R. China · Huakong AI Plus Company Limited, Beijing, 100084, P. R. China +1

Sep 26, 2026, cs.LGJ/K move · Enter open · S save

Fisher Simplicity in Kolmogorov-Arnold Networks and Multilayer Perceptrons

Ami Tavory, Meir Feder

Meta Platforms Tel-Aviv, Israel · School of Electrical and Computer Engineering Tel-Aviv University Tel-Aviv, Israel

Kolmogorov-Arnold Networks Multilayer Perceptrons Fisher Information Simplification Structured Pruning

Open paper AskPDF arXiv

Kolmogorov-Arnold Networks (KANs) are motivated in part by interpretability: their learned edge functions can be inspected, pruned, and reduced to symbolic structure. In a fixed-basis KAN, this makes a small or zero basis coefficient look like a certificate of simplicity, much as a dead rectified linear unit (ReLU) marks unused computation in a multilayer perceptron (MLP). Fisher nullity gives a precise statistical notion: a parameter direction is Fisher-simple exactly when perturbing it is invisible under the task distribution. We study when these architectural and Fisher notions agree. For a dead ReLU unit, they agree: the closed activation region makes the associated score directions vanish. For a fixed-basis KAN, they do not. In the single-layer Gaussian case, the coefficient Fisher matrix is a basis Gram matrix under the input distribution and is independent of the fitted coefficients. In a multilayer KAN, Fisher simplicity is graph-path based: the data must reach a basis atom and its perturbation must propagate through the downstream network. We encode these two conditions in an effective edge measure and, under local dictionary independence and effective-measure nondegeneracy, show that zero effective exposure exactly identifies Fisher-null directions within an edge. Controlled diagnostics confirm that zero coefficients can preserve rank while effective path disconnections remove the predicted directions. Coefficient magnitude alone is therefore not a Fisher-based pruning criterion for KANs.

Momentum

Related topics

Latest papers 22